Sheng-Wei Zhang, Hsi-An Chen, Yan-Ting Liou, Chih-Hsuan Chen, Shih-Chen Tseng, Yu-Lun Liu · 2026 · arXiv (Cornell University)
DOI: 10.48550/arxiv.2610.26851 · cited by 0 works (OpenAlex) · open-access PDF
Adapter le manga existant en une animation cohérente qui reste fidèle à la source est une tâche précieuse mais difficile. Les méthodes existantes accèdent soit au manga principalement par le texte, en perdant ses personnages et son style d'art, soit alimentent des pages de manga directement dans des modèles de génération vidéo, qui interprètent mal la structure du manga et produisent des lignes d'histoire incorrectes. Dans ce document, nous proposons Manga2Animate, un cadre multi-agent qui fonde chaque étape de la génération dans le manga source. Nous décomposons la tâche en deux représentations intermédiaires, un script d'animation et un storyboard visuel. Chaque représentation est produite par un créateur et examinée contre les panneaux de source par un agent d'examen en pair.
Machine translation (Meta M2M100); the English original follows.
Adapting existing manga into coherent animation that stays faithful to the source is a valuable yet challenging task. Existing methods either access the manga mainly through text, losing its characters and art style, or feed manga pages directly into video generation models, which misinterpret the manga's structure and produce incorrect storylines. In this paper, we propose Manga2Animate, a multi-agent framework that grounds every stage of generation in the source manga. We decompose the task into two intermediate representations, an animation script and a visual storyboard. Each representation is produced by a creator agent and reviewed against the source panels by a paired reviewer agent. We tailor representation-specific selection and dual-level feedback to progressively refine both before synthesizing the final animation. Extensive experiments and a user study demonstrate that Manga2Animate produces animations more faithful to the source manga and more consistent across shots than state-of-the-art approaches. Project page: https://annchenn.github.io/Manga2Animate/
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
Topics: Storyboard, Computer science, Animation, Selection (genetic algorithm), Representation (politics), Task (project management)
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.26851, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange